csm-english-multi-speaker-v2

onecxi/csm-english-multi-speaker-v2

Text to Speech1.6B parameterstransformersLicense: apache-2.0

Tracked by OpenModelStats since September 8, 2026View on Hugging Face ↗

Downloads 30D: 55
Total downloads: 4,664
Gained 7D: +16(increase); 0.3%(up) vs baseline
Gained 30D: —
Likes: 3; +0 in 7D
Rank · tracked models: —; –this week
Parameters: 1.6B
Last source update: Jul 13, 2025

csm-english-multi-speaker-v2 gained 16 downloads during the last seven tracked days.

7D 30D 90D 1Y All

Total downloads Gained per day Rolling recent downloads

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-09-08. Charts appear as daily observations accumulate.

Overview

csm-english-multi-speaker-v2 is a text to speech model published by onecxi. OpenModelStats has tracked the model since Sep 8, 2026, most recently observing it Sep 15, 2026.

Published: Jul 3, 2025
Last updated: Jul 13, 2025
Library: transformers
License: apache-2.0
Task: Text to Speech
Parameters: 1,648,942,945
Spaces: —
Derivative models: —
Velocity 7D/day: 2

transformerssafetensorscsmtext-to-audiotext-to-speechendataset:reach-vb/jenny_tts_datasetdataset:ylacombe/expressobase_model:sesame/csm-1bbase_model:finetune:sesame/csm-1blicense:apache-2.0endpoints_compatible

Publisher

onecxiView publisher statistics →

Derived from sesame/csm-1b (reported by the source; parent not yet tracked).

Similar models

Models similar to csm-english-multi-speaker-v2
Model	Task	DL 30D	Likes	Params
csm-1bunsloth	Text to Speech	7,018	23	1.6B
csm-1b-danish-ttsnicolajreck	Text to Speech	284	5	1.6B
Zonos-v0.1-hybridZyphra	Text to Speech	1,116	1,109	1.7B
Zonos-v0.1-transformerZyphra	Text to Speech	41.3K	436	1.6B
Ming-omni-tts-0.5BinclusionAI	Text to Speech	24.2K	39	1.6B
Dia-1.6Bnari-labs	Text to Speech	27.5K	2,916	1.6B